Neural machine translation for low-resource languages

Abstract

Neural machine translation (NMT) approaches have improved the state of the art in many machine translation settings over the last couple of years, but they require large amounts of training data to produce sensible output. We demonstrate that NMT can be used for low-resource languages as well, by introducing more local dependencies and using word alignments to learn sentence reordering during translation. In addition to our novel model, we also present an empirical evaluation of low-resource phrase-based statistical machine translation (SMT) and NMT to investigate the lower limits of the respective technologies. We find that while SMT remains the best option for low-resource settings, our method can produce acceptable translations with only 70000 tokens of training data, a level where the baseline NMT system fails completely.

rejected from EMNLP 2017

Cited by in corpus (9)

• Revisiting Low-Resource Neural Machine Translation: A Case Study
• Polyglot Semantic Parsing in APIs
• Low-Resource Neural Machine Translation for Southern African Languages
• Neural Machine Translation: A Review and Survey
• Low-Resource Syntactic Transfer with Unsupervised Source Reordering
• Exploring Pair-Wise NMT for Indian Languages
• Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation
• Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation
• Understanding and Enhancing the Use of Context for Machine Translation